Post-Training Gemini 4 for Real Engineering Work — Melvin Johnson, Google DeepMind
Source
youtube.com
Author
AI Engineer
Date
Why it matters
Explains how a frontier lab grades coding agents without rewarding test gaming and trains them to report honestly, which shows what to expect from and how to evaluate AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → output.
Terms in this piece · Glossary
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.